Merge pull request #106 from Guovin/dev

Release: v1.1.2

.github/workflows/main.yml

@@ -18,7 +18,7 @@ jobs:
     steps:
       - name: Set branch name
         id: vars
-        run: echo ::set-output name=branch::${{ github.ref == 'refs/heads/gd' && 'gd' || 'master' }}
+        run: echo ::set-output name=branch::${{ github.repository_owner == 'Guovin' && 'gd' || 'master' }}
       - uses: actions/checkout@v3
         with:
           ref: ${{ steps.vars.outputs.branch }}

CHANGELOG.md

@@ -1,5 +1,13 @@
 # 更新日志（Changelog）
 
+## v1.1.2
+
+### 2024/5/7
+
+- 重构接口获取方法，增强通用性，适应结构变更（Refactored the method for obtaining the interface, enhanced its universality, and adapted to structural changes）
+- 修复 gd 分支自动更新问题（#105）（Fixed the automatic update issue of the gd branch (#105)）
+- 优化自定义接口源获取，接口去重（Optimized the acquisition of custom interface sources and removed duplicate interfaces）
+
 ## v1.1.1
 
 ### 2024/4/29

main.py

@@ -8,12 +8,13 @@
 from selenium.webdriver.support import expected_conditions as EC
 from selenium_stealth import stealth
 import asyncio
-from bs4 import BeautifulSoup
+from bs4 import BeautifulSoup, NavigableString
 from utils import (
     getChannelItems,
     updateChannelUrlsTxt,
     updateFile,
-    getUrlInfo,
+    getChannelUrl,
+    getChannelInfo,
     sortUrlsBySpeedAndResolution,
     getTotalUrls,
     filterUrlsByPatterns,
@@ -25,6 +26,7 @@
 from logging.handlers import RotatingFileHandler
 import os
 from tqdm import tqdm
+import re
 
 handler = RotatingFileHandler("result_new.log", encoding="utf-8")
 logging.basicConfig(
@@ -114,18 +116,37 @@ async def visitPage(self, channelItems):
                                 self.driver.execute_script(
                                     "arguments[0].click();", page_link
                                 )
-                            soup = BeautifulSoup(self.driver.page_source, "html.parser")
-                            results = (
-                                soup.find_all("div", class_="result") if soup else []
+                            source = re.sub(
+                                r"<!--.*?-->",
+                                "",
+                                self.driver.page_source,
+                                flags=re.DOTALL,
                             )
-                            for result in results:
-                                try:
-                                    url, date, resolution = getUrlInfo(result)
+                            soup = BeautifulSoup(source, "html.parser")
+                            if soup:
+                                results = []
+                                for element in soup.descendants:
+                                    if isinstance(element, NavigableString):
+                                        url = getChannelUrl(element)
+                                        if url and not any(
+                                            item[0] == url for item in results
+                                        ):
+                                            url_element = soup.find(
+                                                lambda tag: tag.get_text(strip=True)
+                                                == url
+                                            )
+                                            if url_element:
+                                                info_element = (
+                                                    url_element.find_next_sibling()
+                                                )
+                                                date, resolution = getChannelInfo(
+                                                    info_element
+                                                )
+                                                results.append((url, date, resolution))
+                                for result in results:
+                                    url, date, resolution = result
                                     if url and checkUrlByPatterns(url):
                                         infoList.append((url, date, resolution))
-                                except Exception as e:
-                                    print(f"Error on result {result}: {e}")
-                                    continue
                         except Exception as e:
                             print(f"Error on page {page}: {e}")
                             continue

utils.py

@@ -91,7 +91,8 @@ async def getChannelsByExtendBaseUrls(channel_names):
                         url = re.match(pattern, line).group(2)
                         value = (url, None, resolution)
                         if key in link_dict:
-                            link_dict[key].append(value)
+                            if value not in link_dict[key]:
+                                link_dict[key].append(value)
                         else:
                             link_dict[key] = [value]
                 found_channels = []
@@ -137,31 +138,37 @@ def updateFile(final_file, old_file):
         os.replace(old_file, final_file)
 
 
-def getUrlInfo(result):
+def getChannelUrl(element):
     """
     Get the url, date and resolution
     """
-    url = date = resolution = None
-    result_div = [div for div in result.children if div.name == "div"]
-    if 1 < len(result_div):
-        channel_text = result_div[1].get_text(strip=True)
-        url_match = re.search(
-            r"http[s]?://(?:[a-zA-Z]|[0-9]|[$-_@.&+]|[!*\\(\\),]|(?:%[0-9a-fA-F][0-9a-fA-F]))+",
-            channel_text,
+    url = None
+    urlRegex = r"http[s]?://(?:[a-zA-Z]|[0-9]|[$-_@.&+]|[!*\\(\\),]|(?:%[0-9a-fA-F][0-9a-fA-F]))+"
+    url_search = re.search(
+        urlRegex,
+        element.get_text(strip=True),
+    )
+    if url_search:
+        url = url_search.group()
+    return url
+
+
+def getChannelInfo(element):
+    """
+    Get the channel info
+    """
+    date, resolution = None, None
+    info_text = element.get_text(strip=True)
+    if info_text:
+        date, resolution = (
+            (info_text.partition(" ")[0] if info_text.partition(" ")[0] else None),
+            (
+                info_text.partition(" ")[2].partition("•")[2]
+                if info_text.partition(" ")[2].partition("•")[2]
+                else None
+            ),
         )
-        if url_match is not None:
-            url = url_match.group()
-        info_text = result_div[-1].get_text(strip=True)
-        if info_text:
-            date, resolution = (
-                (info_text.partition(" ")[0] if info_text.partition(" ")[0] else None),
-                (
-                    info_text.partition(" ")[2].partition("•")[2]
-                    if info_text.partition(" ")[2].partition("•")[2]
-                    else None
-                ),
-            )
-    return url, date, resolution
+    return date, resolution
 
 
 async def getSpeed(url, urlTimeout=5):

version.json

@@ -1,3 +1,3 @@
 {
-  "version": "1.1.1"
+  "version": "1.1.2"
 }